SOTAVerified

Neural Architecture Search

Neural architecture search (NAS) is a technique for automating the design of artificial neural networks (ANN), a widely used model in the field of machine learning. NAS essentially takes the process of a human manually tweaking a neural network and learning what works well, and automates this task to discover more complex architectures.

Image Credit : NAS with Reinforcement Learning

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1601–1650 of 1915 papers

TitleStatusHype
Automated Fusion of Multimodal Electronic Health Records for Better Medical PredictionsCode0
Cascade Bagging for Accuracy Prediction with Few Training SamplesCode0
Generalizable Learning Reconstruction for Accelerating MR Imaging via Federated Neural Architecture SearchCode0
Partial Order Pruning: for Best Speed/Accuracy Trade-off in Neural Architecture SearchCode0
Search to Capture Long-range Dependency with Stacking GNNs for Graph ClassificationCode0
PaRT: Parallel Learning Towards Robust and Transparent AICode0
Learning to reinforcement learn for Neural Architecture SearchCode0
Learning Transferable Architectures for Scalable Image RecognitionCode0
Gait Recognition in the Wild: A Large-scale Benchmark and NAS-based BaselineCode0
Fusion Matters: Learning Fusion in Deep Click-through Rate Prediction ModelsCode0
Learning to Rank Ace Neural Architectures via Normalized Discounted Cumulative GainCode0
CARS: Continuous Evolution for Efficient Neural Architecture SearchCode0
PASHA: Efficient HPO and NAS with Progressive Resource AllocationCode0
LENAS: Learning-based Neural Architecture Search and Ensemble for 3D Radiotherapy Dose PredictionCode0
PASTA: Neural Architecture Search for Anomaly Detection in Multivariate Time SeriesCode0
Less is More: Proxy Datasets in NAS approachesCode0
Path-Level Network Transformation for Efficient Architecture SearchCode0
PC-DARTS: Partial Channel Connections for Memory-Efficient Architecture SearchCode0
AutoLC: Search Lightweight and Top-Performing Architecture for Remote Sensing Image Land-Cover ClassificationCode0
SEDONA: Search for Decoupled Neural Networks toward Greedy Block-wise LearningCode0
Lifelong Learning with Searchable Extension UnitsCode0
Neural Architecture Search via Two Constant Shared Weights InitialisationsCode0
FTT-NAS: Discovering Fault-Tolerant Convolutional Neural ArchitectureCode0
From Xception to NEXcepTion: New Design Decisions and Neural Architecture SearchCode0
Unleashing the Power of Gradient Signal-to-Noise Ratio for Zero-Shot NASCode0
FlatNAS: optimizing Flatness in Neural Architecture Search for Out-of-Distribution RobustnessCode0
CAP: A Context-Aware Neural Predictor for NASCode0
Finding Non-Uniform Quantization Schemes using Multi-Task Gaussian ProcessesCode0
Lightweight Neural Architecture Search for Cerebral Palsy DetectionCode0
The Evolved TransformerCode0
Feature Pyramid GridsCode0
3D-ANAS: 3D Asymmetric Neural Architecture Search for Fast Hyperspectral Image ClassificationCode0
Unsupervised Domain Adaptation Architecture Search with Self-Training for Land Cover MappingCode0
PIDS: Joint Point Interaction-Dimension Search for 3D Point CloudCode0
FBNetV3: Joint Architecture-Recipe Search using Predictor PretrainingCode0
CAE-ADMM: Implicit Bitrate Optimization via ADMM-based Pruning in Compressive AutoencodersCode0
Butterfly Transform: An Efficient FFT Based Neural Architecture DesignCode0
LLM Performance Predictors are good initializers for Architecture SearchCode0
Fast Neural Network Adaptation via Parameter Remapping and Architecture SearchCode0
FasterSeg: Searching for Faster Real-time Semantic SegmentationCode0
Building Optimal Neural Architectures using Interpretable KnowledgeCode0
DDPNAS: Efficient Neural Architecture Search via Dynamic Distribution PruningCode0
Long-term Reproducibility for Neural Architecture SearchCode0
The OCON model: an old but gold solution for distributable supervised classificationCode0
Self-Supervised Neural Architecture Search for Imbalanced DatasetsCode0
Self-supervised Representation Learning for Evolutionary Neural Architecture SearchCode0
PONAS: Progressive One-shot Neural Architecture Search for Very Efficient DeploymentCode0
Budgeted Training: Rethinking Deep Neural Network Training Under Resource ConstraintsCode0
Semi-discrete optimization through semi-discrete optimal transport: a framework for neural architecture searchCode0
Manas: Mining Software Repositories to Assist AutoMLCode0
Show:102550
← PrevPage 33 of 39Next →
All datasetsImageNetNAS-Bench-201, ImageNet-16-120CIFAR-10NAS-Bench-201, CIFAR-100NAS-Bench-201, CIFAR-10CIFAR-10 Image ClassificationCIFAR-100NATS-Bench Topology, CIFAR-10NATS-Bench Topology, CIFAR-100NATS-Bench Topology, ImageNet16-120Food-101NAS-Bench-101

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1SPOS (ProxylessNAS (GPU) latency)Accuracy75.3—Unverified
2SPOS (FBNet-C latency)Accuracy75.1—Unverified
3SPOS (block search + channel search)Accuracy74.7—Unverified
4MUXNet-xsTop-1 Error Rate33.3—Unverified
5FBNetV2-F1Top-1 Error Rate31.7—Unverified
6LayerNAS-60MTop-1 Error Rate31—Unverified
7NASGEPTop-1 Error Rate29.51—Unverified
8MUXNet-sTop-1 Error Rate28.4—Unverified
9NN-MASS-ATop-1 Error Rate27.1—Unverified
10FBNetV2-F3Top-1 Error Rate26.8—Unverified
#ModelMetricClaimedVerifiedStatus
1CR-LSOAccuracy (Test)46.98—Unverified
2Shapley-NASAccuracy (Test)46.85—Unverified
3β-RDARTS-L2Accuracy (Test)46.71—Unverified
4β-SDARTS-RSAccuracy (Test)46.71—Unverified
5ASE-NAS+Accuracy (Val)46.66—Unverified
6NARAccuracy (Test)46.66—Unverified
7BaLeNAS-TFAccuracy (Test)46.54—Unverified
8AG-NetAccuracy (Test)46.42—Unverified
9Local searchAccuracy (Test)46.38—Unverified
10NASBOTAccuracy (Test)46.37—Unverified
#ModelMetricClaimedVerifiedStatus
1Balanced MixtureAccuracy (% )91.55—Unverified
2GDASTop-1 Error Rate3.4—Unverified
3Bonsai-NetTop-1 Error Rate3.35—Unverified
4Net2 (2)Top-1 Error Rate3.3—Unverified
5μDARTSTop-1 Error Rate3.28—Unverified
6NN-MASS- CIFAR-CTop-1 Error Rate3.18—Unverified
7NN-MASS- CIFAR-ATop-1 Error Rate3—Unverified
8DARTS (first order)Top-1 Error Rate3—Unverified
9NASGEPTop-1 Error Rate2.82—Unverified
10AlphaX-1 (cutout NASNet)Top-1 Error Rate2.82—Unverified